Learning Through Experimentation: A Look at Two New Big Data Innovation Projects
This is Part I of a series of posts on a collaboration between UN Global Pulse and the Packard Foundation. The collaboration emphasized the “learning by doing” process of designing a big data project, and tested the value of leveraging new sources of digital data to understand public perceptions. Read Part II about design process, and Part III with reflections on the experience.
UN Global Pulse and the David and Lucile Packard Foundation recently wrapped up two collaborative big data innovation projects. The two experimental projects focused on the “learning by doing” process of designing a big data project, and tested the value of leveraging new sources of digital data to understand public perceptions.
“These projects were intended as an experiment to develop a “proof-of-concept” to demonstrate how data-driven, evidence-based solutions can be applied to real world challenges of tracking progress and completing evaluations,” says Meredith Pearlman, Evaluation & Learning manager with Packard Foundation.
Embarking on a big data for development project entails understanding the existing data gaps within an organization and what possible alternative data sources could fill those gaps or serve as proxies.
After several brainstorming sessions, two topics were selected based on their importance and the limited existing (traditional) information around them. The first project analyzed attitudes towards biofuels, and the second looked at gaining insights on child marriage with online data sources.
Analyzing Attitudes Towards Biofuels With Social Media
The exploration studied whether changes in sentiment around biofuels can be captured using social media. To this end, the project set out to analyze how public perceptions of and attitudes towards biofuels in the UK and Germany evolved over a period of three years, from 2013 to 2015.
While much is known about what events typically drive global conversation around sustainable energy, there exist few quantitative measurements of any overall changes in public opinion that occur as new biofuels techniques are discovered.
The project analysed around 350,000 public tweets from the UK and 35,000 tweets from Germany about biofuels to understand whether any changes occurred in the balance between statements for and against the use of biofuels. The analysis also tried to identify if the stated reasons of being against biofuels changed with the emergence of advanced biofuels.
Read more about the Analyzing Attitudes Towards Biofuels with Social Media project and access the report here
Mining Online Data for Insights on Child Marriage
This project explored the value of analyzing online sources and mainstream media to gain insights on child marriage in two countries faced with this challenging issue, namely Ethiopia and India.
There is limited official data available on the topic and while there is a great deal of digital data worth exploring on the subject, digital information is not always easy to access or effectively analyze in ways that are relevant to programme staff of international organizations.
The project analyzed online data sources - news media, Wikipedia, web searches - and assessed the availability of signals and type of insights that can be extracted about child marriage.
Learn more about the Mining Online Data for Insights on Child Marriage project and view some of the results: childmarriage.unglobalpulse.net
Learning through experimenting
Pinning down a definition of what big data represents, is not without challenges but there is broad consensus that massive increases in data create opportunities to gain new insights. As people use digital devices and platforms to communicate, buy and sell goods, transfer money, and share their lives publicly on social networks, they leave digital trails. If harnessed responsibly, these data trails can be used to design programs and implement operations in real-time.
With this in mind, Global Pulse and the Packard Foundation dedicated time and resources to exploring the basics of how to approach the planning and design of data innovation projects within a social sector organization.
“The two projects—and the exploration as a whole—were a constructive challenge for us. That is, prior to commissioning Global Pulse, our Evaluation & Learning team had little experience with, and understanding of, big data analysis techniques and possibilities. Now, we appreciate the complexity of such analysis, the amount of effort and time that it takes, and the importance of carefully scoping suitable projects as well as diligently managing them,” says Meredith.
This is Part I of a series of posts about a collaboration with the Packard Foundation. Continue on to read Part II of the series which provides a breakdown of the project design process, featuring the child marriage study.